Multi-Transmitter Physical Layer Authentication Using Channel State Information and Deep Learning
Ken St. Germain, Frank E. Kragh · 2020
Efficient authentication across wireless devices improves the security of the overall network and can be accomplished at the physical layer. By stratifying privilege levels for different devices, security is further improved. We propose the use of machine learning and received multiple-input multiple-output communications channel information to identify trusted transmitters. Our approach uses received channel state information at various signal to noise levels from multiple transmitters to train a deep neural network to make an authentication decision. We show that an adversarially-trained classifier network can correctly differentiate among transmitters using very few labeled samples from a greater dataset.